Mihyeon Kim
5 papers · 2023–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(14)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Machine Learning
(4)
Artificial Intelligence
(3)
Core AI
(3)
Deep Learning
(2)
Natural Language Processing
(2)
Architectures
(2)
Optimization & Theory · Machine Learning
(2)
Application Areas
(1)
Applications
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Deep Learning
(1)
Resources & Methods
(1)
Techniques
(1)
Keywords
vision-language model
(2)
continual learning
(1)
adversarial robustness
(1)
attention mechanism
(1)
multimodal learning
(1)
machine unlearning
(1)
model forgetting
(1)
loss landscape
(1)
gradient descent
(1)
document classification
(1)
mahalanobis distance
(1)
adversarial attack
(1)
bias mitigation
(1)
spurious correlation
(1)
numerical stability
(1)
token pruning
(1)
pre-trained language model
(1)
ordinary differential equation
(1)
few-shot class-incremental learning
(1)
token compression
(1)
Papers
Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias
AAAI 2026
HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning
CVPR 2026
See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias
NAACL 2025
IM-BERT: Enhancing Robustness of BERT through the Implicit Euler Method
EMNLP 2024
Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification
EMNLP 2023